One API for approved model services

TEKIZ.AI model gateway

Connect the model services your team uses from one API. TEKIZ.AI can use local Ollama, private servers, and provider accounts your team authorizes. You choose how requests move when a service is unavailable.

Create hosted API key Migration guide Fusion compatibility Compare plans Compare OpenRouter View public edge status Compare plan fit Max implementation review
Recover API key

Create an account now. Connect an authorized provider or add billing when you are ready to route.

Connect only provider accounts and subscriptions you are allowed to use. TEKIZ.AI does not bypass provider terms.

Evaluating OpenRouter specifically? Read the focused TEKIZ.AI vs OpenRouter comparison for hosted catalog access and private model setups.

Keep provider keys in your environment.

Provider credentials can stay on your machine, server, Tailnet, or private router. A hosted TEKIZ.AI account manages its own API keys and billing.

Set clear rules for service outages.

Set the order for each type of work using provider health, response time, model capability, and your local or cloud preference. Use the same API with Codex, OpenClaw, Cursor, Aider, Continue, and OpenAI-compatible tools.

Use local models with cloud services.

Local Ollama and Ollama Cloud can sit beside OpenAI, Anthropic, Gemini, NVIDIA NIM, private services, and other providers your team authorizes.

Comparison

Need TEKIZ.AI Hosted model gateway
Where provider keys live Local-first by default. Provider keys can remain on customer-controlled routers. Typically centralized through the hosted API account.
Coding tool support OpenAI-compatible, Anthropic-compatible, Codex, OpenClaw, Cursor, Aider, Continue, OpenHands, and harness fallback docs. Strong hosted OpenAI-compatible API story.
Local models First-class. Route local Ollama and local/cloud hybrid profiles beside hosted providers. Usually focused on remote hosted model providers.
Provider selection Your team's rules, provider health, response time, model capability, task type, and service order. Model catalog selection and provider routing through hosted infrastructure.
Fusion / compound answers Premium Pro/Max route. Use tekizai/fusion or the tekizai:fusion server tool to derive independent tasks, run them in parallel, and review the result. Compound routing can expose a hosted multi-model workflow.
Resilience model Tailnet and edge routing can select the healthiest TEKIZ.AI Router installation and keep private routers behind the public API edge. Depends on the hosted provider platform and upstream provider health.
Hosted SaaS Hosted signup, Stripe checkout, API keys, usage quotas, status page, analytics, and Supabase-backed auth. Mature hosted account and billing experience.
Best fit Teams with existing provider accounts, local models, private servers, and clear rules for model use. Hosted model marketplace access with minimal local infrastructure.

How to switch

Keep one API address for your tools.

For hosted access, create an account and API key, then point your tools at TEKIZ.AI. For a private setup, run the router on port 8790 and keep provider credentials on your machine or Tailnet host. 

export OPENAI_BASE_URL="https://api.tekiz.ai/v1"
export OPENAI_API_KEY="sk_tekiz_..."

curl "$OPENAI_BASE_URL/chat/completions" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tekizai/frontier",
    "messages": [{"role": "user", "content": "Route this well"}]
  }'
Copy setup first. Paste the bundle into your current OpenAI-compatible client, then replace the placeholder with your generated sk_tekiz_* key.

Hosted plans

Hosted plans for teams using their own providers.

Hosted plans add API keys, activity records, service order, shared team settings, and support. The open-source router remains available for local and private setups.

  • Lite: hosted access and activity visibility for individual workflows.
  • Pro: advanced model choices, Fusion when capacity is live, service-order controls, and activity records for development work.
  • Max: high-volume automation, priority service order, Fusion when capacity is live, and team use.
  • Max implementation review: request migration help, private deployment support, or future one-subscription model access only after provider authorization, margin, quota, operator-audit, and abuse-control gates are ready. Request private-beta review.